Dicty analysis

library(ggplot2)
library(RVenn)

# load the data and visualization functions
source("global.R")
source("../utils/visualization_functions.R")

Normalised spectral count per group and total, add columns to dataframe

# Z-score normalisation, by group and total
all_data_dicty <- all_data_dicty %>% 
  group_by(bait, condition) %>% 
  mutate(grouped_z_score_spectral = scale(spectral_count))

all_data_dicty <- all_data_dicty %>% 
  mutate(z_score_spectral = scale(spectral_count))

summary

Summary statistics Dicty

all_data_dicty %>% 
  summarise(Unique_bait = n_distinct(bait))

## `summarise()` regrouping output by 'bait' (override with `.groups` argument)

## # A tibble: 15 x 3
## # Groups:   bait [12]
##    bait    condition  Unique_bait
##    <fct>   <fct>            <int>
##  1 Galpha2 starv                1
##  2 Galpha2 veg                  1
##  3 Galpha4 Normal               1
##  4 Galpha8 GDP                  1
##  5 Galpha8 GppNHp               1
##  6 Galpha8 Normal               1
##  7 Gbeta1  Normal               1
##  8 Gbeta2  Normal               1
##  9 Rac1    Normal               1
## 10 RapA    Normal               1
## 11 RasB    Normal               1
## 12 RasC    Normal               1
## 13 RasG1   Normal               1
## 14 Ric8    Normal               1
## 15 Roco4   BACKGROUND           1

Show the unique baits count

all_data_dicty %>% 
  group_by(bait, condition) %>% 
  tidyr::unite(bait_condition, c(bait, condition), sep = '_') %>% 
  summarise(Unique_bait_condition = n_distinct(bait_condition))

## # A tibble: 1 x 1
##   Unique_bait_condition
##                   <int>
## 1                    15

Show how many instances (lines) of bait there are

table(all_data_dicty$bait)

## 
## Galpha2 Galpha4 Galpha8  Gbeta1  Gbeta2    Rac1    RapA    RasB    RasC   RasG1 
##    3206    1603    4100     876     876    1448     461     808     998     337 
##    Ric8   Roco4 
##    1448    1448

Show how many instances (lines) of condition there are

table(all_data_dicty$condition)

## 
## BACKGROUND        GDP     GppNHp     Normal      starv        veg 
##       1448       1436       1436      10083       1603       1603

Show total spectral count per bait + condition

all_data_dicty %>% 
  group_by(bait, condition) %>% 
  summarise(.groups = 'drop', across(spectral_count, sum))

## # A tibble: 15 x 3
##    bait    condition  spectral_count
##    <fct>   <fct>               <dbl>
##  1 Galpha2 starv               20155
##  2 Galpha2 veg                 30986
##  3 Galpha4 Normal              27070
##  4 Galpha8 GDP                 13099
##  5 Galpha8 GppNHp              23136
##  6 Galpha8 Normal              23324
##  7 Gbeta1  Normal              16390
##  8 Gbeta2  Normal              20644
##  9 Rac1    Normal              22196
## 10 RapA    Normal               5238
## 11 RasB    Normal              12182
## 12 RasC    Normal              22778
## 13 RasG1   Normal              12369
## 14 Ric8    Normal              18323
## 15 Roco4   BACKGROUND          19376

Show normalized spectral count per bait + condition

all_data_dicty %>% 
  group_by(bait, condition) %>% 
  summarise(.groups = 'drop', across(z_score_spectral, sum))

## # A tibble: 15 x 3
##    bait    condition  z_score_spectral
##    <fct>   <fct>                 <dbl>
##  1 Galpha2 starv              9.37e-16
##  2 Galpha2 veg                1.30e-14
##  3 Galpha4 Normal             7.91e-16
##  4 Galpha8 GDP               -2.50e-14
##  5 Galpha8 GppNHp             4.31e-14
##  6 Galpha8 Normal             1.87e-14
##  7 Gbeta1  Normal             1.72e-14
##  8 Gbeta2  Normal             7.63e-15
##  9 Rac1    Normal             7.24e-15
## 10 RapA    Normal            -1.07e-14
## 11 RasB    Normal             1.05e-14
## 12 RasC    Normal            -2.95e-15
## 13 RasG1   Normal            -4.02e-15
## 14 Ric8    Normal            -4.04e-15
## 15 Roco4   BACKGROUND         1.28e-15

# this does not look correct, we should normalize by total spectral count?, can we sum z-scores?

Show how many uniq uniprot id’s are in the set (dicty has 6 chromosomes and 12500 proteins)

n_distinct(all_data_dicty$uniprot)

## [1] 2988

uniq proteins per bait_condition

bait_condition <- group_by(all_data_dicty, bait, condition)

bait_condition %>% 
  summarise(n_distinct(uniprot))

## `summarise()` regrouping output by 'bait' (override with `.groups` argument)

## # A tibble: 15 x 3
## # Groups:   bait [12]
##    bait    condition  `n_distinct(uniprot)`
##    <fct>   <fct>                      <int>
##  1 Galpha2 starv                       1603
##  2 Galpha2 veg                         1603
##  3 Galpha4 Normal                      1603
##  4 Galpha8 GDP                         1436
##  5 Galpha8 GppNHp                      1436
##  6 Galpha8 Normal                      1228
##  7 Gbeta1  Normal                       876
##  8 Gbeta2  Normal                       876
##  9 Rac1    Normal                      1448
## 10 RapA    Normal                       461
## 11 RasB    Normal                       808
## 12 RasC    Normal                       998
## 13 RasG1   Normal                       337
## 14 Ric8    Normal                      1448
## 15 Roco4   BACKGROUND                  1448

Unique proteins per condition

group_by(all_data_dicty, condition) %>% 
  summarise(n_distinct(uniprot))

## `summarise()` ungrouping output (override with `.groups` argument)

## # A tibble: 6 x 2
##   condition  `n_distinct(uniprot)`
##   <fct>                      <int>
## 1 BACKGROUND                  1448
## 2 GDP                         1436
## 3 GppNHp                      1436
## 4 Normal                      2933
## 5 starv                       1603
## 6 veg                         1603

Unique proteins per bait

group_by(all_data_dicty, bait) %>% 
  summarise(n_distinct(uniprot))

## `summarise()` ungrouping output (override with `.groups` argument)

## # A tibble: 12 x 2
##    bait    `n_distinct(uniprot)`
##    <fct>                   <int>
##  1 Galpha2                  1603
##  2 Galpha4                  1603
##  3 Galpha8                  1446
##  4 Gbeta1                    876
##  5 Gbeta2                    876
##  6 Rac1                     1448
##  7 RapA                      461
##  8 RasB                      808
##  9 RasC                      998
## 10 RasG1                     337
## 11 Ric8                     1448
## 12 Roco4                    1448

absolute spectral count

Barplot showing the total spectral count for each bait

p <- ggplot(all_data_dicty, aes(x=bait, y =spectral_count))
p <- p + geom_col() + labs(title = 'Spectral count vs bait')
p

Barplot showing the absolute spectral count for each condition

p <- ggplot(all_data_dicty, aes(x=condition, y =spectral_count))
p <- p + geom_col() + labs(title = 'Spectral count vs condition')
p

Combined spectral count for bait + condition, sum spectral count per group

my_data <-all_data_dicty %>% group_by(bait, condition) %>% 
    # .groups = drop is the default, will get warnings if you not specify explicitly 
    summarise(.groups = 'drop', across(spectral_count, sum)) %>% 
    tidyr::unite(bait_condition, c(bait, condition), sep = "_")
  
p <- ggplot(my_data, aes(x = bait_condition, y = spectral_count))
p <- p + geom_col() + labs(title = 'spectral count vs bait + condition')
p + theme(axis.text.x = element_text(angle = 45, hjust = 1))

average spectra

Barplot showing the average spectral count per protein for each bait divided the summed group count by the number of observations in that group so avg count per group

# get group sizes
group_spectra_normalized <- all_data_dicty %>% 
  group_by(bait) %>% 
  summarise(sum_spectra = sum(spectral_count), group_size = n(), average_spectra = sum(spectral_count/n()))

## `summarise()` ungrouping output (override with `.groups` argument)

p <- ggplot(group_spectra_normalized, aes(x=bait, y = average_spectra))
p <- p + geom_col() + labs(title = 'average Spectral count per bait')
p

Barplot showing the average spectral count for each condition: divided the summed group count by the number of observations in that group,

# get group sizes
group_spectra_normalized <- all_data_dicty %>% 
  group_by(condition) %>% 
  summarise(sum_spectra = sum(spectral_count), group_size = n(), average_spectra = sum(spectral_count/n()))

## `summarise()` ungrouping output (override with `.groups` argument)

p <- ggplot(group_spectra_normalized, aes(x=condition, y=average_spectra))
p <- p + geom_col() + labs(title = 'average Spectral count vs condition')
p

# get group sizes
group_spectra_normalized <- all_data_dicty %>% 
  group_by(bait, condition) %>% 
  summarise(sum_spectra = sum(spectral_count), group_size = n(), average_spectra = sum(spectral_count/n())) %>% 
  tidyr::unite(bait_condition, c(bait, condition), sep = "_")

## `summarise()` regrouping output by 'bait' (override with `.groups` argument)

p <- ggplot(group_spectra_normalized, aes(x = bait_condition, y = average_spectra))
p <- p + geom_col() + labs(title = 'average spectral count vs bait + condition')
p + theme(axis.text.x = element_text(angle = 45, hjust = 1))

Combined spectral count for bait + condition, average spectral count per group

# get group sizes
group_spectra_normalized <- all_data_dicty %>% 
  group_by(bait, condition) %>% 
  summarise(sum_spectra = sum(spectral_count), group_size = n(), normalized_spectra = sum(spectral_count/n()), unique_proteins = n_distinct(uniprot)) %>% 
  tidyr::unite(bait_condition, c(bait, condition), sep = "_")

## `summarise()` regrouping output by 'bait' (override with `.groups` argument)

p <- ggplot(group_spectra_normalized, aes(x = bait_condition, y = normalized_spectra))
p <- p + geom_col() + labs(title = 'average spectral count vs bait + condition') +
geom_text(aes(label=unique_proteins), vjust=0)

p + theme(axis.text.x = element_text(angle = 45, hjust = 1))

boxplot bait absolute count

Boxplot absolute count vs bait

p <- ggplot(all_data_dicty, aes(x=bait, y =log10(spectral_count)))
p <- p + geom_boxplot(outlier.colour = "black") + labs(title = 'Spectral count vs bait')
p

## Warning: Removed 3896 rows containing non-finite values (stat_boxplot).

boxplot condition absolute count

Boxplot count vs condition

p <- ggplot(all_data_dicty, aes(x=condition, y =log10(spectral_count)))
p <- p + geom_boxplot(outlier.colour = "black") + labs(title = 'Spectral count vs condition')
p

## Warning: Removed 3896 rows containing non-finite values (stat_boxplot).

boxplot experiment absolute count

Boxplot combined spectral count for bait + condition

my_data <-all_data_dicty %>% 
  group_by(bait, condition) %>% 
    tidyr::unite(bait_condition, c(bait, condition), sep = "_")

my_data$bait_condition <- as.factor(my_data$bait_condition)
p <- ggplot(my_data, aes(x = bait_condition, y = log10(spectral_count)))

p <- p + geom_boxplot(outlier.colour = "black") + labs(title = 'spectral count vs bait + condition')

p + theme(axis.text.x = element_text(angle = 45, hjust = 1))

## Warning: Removed 3896 rows containing non-finite values (stat_boxplot).

z-score normalized boxplot count vs bait

p <- ggplot(all_data_dicty, aes(x=bait, y =log2(z_score_spectral)))
p <- p + geom_boxplot(outlier.colour = "black") + labs(title = 'normalized Spectral count vs bait')
p

## Warning in FUN(X[[i]], ...): NaNs produced

## Warning in FUN(X[[i]], ...): NaNs produced

## Warning: Removed 14596 rows containing non-finite values (stat_boxplot).

z-score normalized boxplot count vs condition

boxplot count vs condition

p <- ggplot(all_data_dicty, aes(x=condition, y =log2(z_score_spectral)))
p <- p + geom_boxplot(outlier.colour = "black") + labs(title = 'normalized Spectral count vs condition')
p

## Warning in FUN(X[[i]], ...): NaNs produced

## Warning in FUN(X[[i]], ...): NaNs produced

## Warning: Removed 14596 rows containing non-finite values (stat_boxplot).

z-score normalized boxplot boxplot count vs experiment

my_data <-all_data_dicty %>% 
  group_by(bait, condition) %>% 
    tidyr::unite(bait_condition, c(bait, condition), sep = "_")

my_data$bait_condition <- as.factor(my_data$bait_condition)

p <- ggplot(my_data, aes(x = bait_condition, y = log2(z_score_spectral)))
p <- p + geom_boxplot(outlier.colour = "black") + labs(title = 'normalized spectral count vs bait + condition')
p + theme(axis.text.x = element_text(angle = 45, hjust = 1))

## Warning in FUN(X[[i]], ...): NaNs produced

## Warning in FUN(X[[i]], ...): NaNs produced

## Warning: Removed 14596 rows containing non-finite values (stat_boxplot).

Venn diagrams

Venn diagrams over bait

bait <- split(all_data_dicty$uniprot, all_data_dicty$bait)
toy_bait = Venn(bait)
ggvenn(toy_bait, slice = c(1, 2,4))

Venn diagrams over condition

condition <- split(all_data_dicty$uniprot, all_data_dicty$condition)
toy_condition = Venn(condition)
ggvenn(toy_condition, slice = c(1, 2,4))

overlap proteins per bait_condition

my_data <-all_data_dicty %>% group_by(bait, condition) %>% tidyr::unite(bait_condition, c(bait, condition), sep = "_")


bait_condition <- split(my_data$uniprot, my_data$bait_condition)
toy = Venn(bait_condition)
#setmap(toy) # to many uniprot ids to show on the axis, needs filtering
ggvenn(toy, slice = c(1, 2,4))

# get character vector with overlapping proteins 
overlap(toy, c("Galpha2_starv", "Galpha2_veg", "Galpha8_GDP", "Gbeta1_Normal"))

##   [1] "GST"                              "sp|P0A6F5|CH60_ECOLI"            
##   [3] "sp|P0A6Y8|DNAK_ECOLI"             "sp|P34042|GPA4_DICDI"            
##   [5] "sp|P07830|ACT1_DICDI"             "gi|136429|sp|P00761|TRYP_PIG"    
##   [7] "tr|B0G141|B0G141_DICDI"           "gi|7428712|pir||KRHU2"           
##   [9] "sp|Q556G3|GSTA2_DICDI"            "gi|81175178|sp|P35527|K1C9_HUMAN"
##  [11] "gi|547749|sp|P13645|K1C10_HUMAN"  "sp|P18624|EF1A_DICDI"            
##  [13] "sp|P54657|CAD1_DICDI"             "sp|Q9GRF8|EF1B_DICDI"            
##  [15] "sp|P36415|HS7C1_DICDI"            "gi|547754|sp|P35908|K22E_HUMAN"  
##  [17] "sp|Q869W9|PKS16_DICDI"            "sp|P15112|EF2_DICDI"             
##  [19] "sp|Q54VI4|GSTA3_DICDI"            "sp|P42530|DIS2_DICDI"            
##  [21] "sp|P54651|HSC90_DICDI"            "sp|Q94469|G3P_DICDI"             
##  [23] "sp|P05095|ACTNA_DICDI"            "sp|Q54D04|MDHB_DICDI"            
##  [25] "sp|P54638|ARGE_DICDI"             "sp|Q55CS9|ATPB_DICDI"            
##  [27] "sp|Q553V1|CISYM_DICDI"            "sp|P10819|SAHH_DICDI"            
##  [29] "sp|P22887|NDKC_DICDI"             "sp|Q557E0|HS7C2_DICDI"           
##  [31] "sp|Q54JC8|PUR4_DICDI"             "sp|P20054|PYR1_DICDI"            
##  [33] "sp|P02887|DIS1B_DICDI"            "sp|P13466|GELA_DICDI"            
##  [35] "sp|P02931|OMPF_ECOLI"             "sp|Q54F07|METK_DICDI"            
##  [37] "sp|Q54RK5|ENOA_DICDI"             "sp|P24639|ANXA7_DICDI"           
##  [39] "sp|Q75JR2|IDHP_DICDI"             "sp|Q86A67|ALF_DICDI"             
##  [41] "sp|P54632|1433_DICDI"             "sp|Q556J0|TKT_DICDI"             
##  [43] "sp|Q8I0H7|HSP7M_DICDI"            "sp|Q54F93|MPPA2_DICDI"           
##  [45] "sp|P15064|RASG_DICDI"             "sp|Q4W6B5|MPPB_DICDI"            
##  [47] "tr|Q54RZ4|Q54RZ4_DICDI"           "sp|Q54VI3|GLUD2_DICDI"           
##  [49] "sp|Q55DV9|CGL_DICDI"              "tr|P90529|P90529_DICDI"          
##  [51] "sp|Q557D2|G6PD_DICDI"             "sp|Q55FF3|GSTA1_DICDI"           
##  [53] "sp|Q23858|CALR_DICDI"             "sp|Q9XPJ9|ATPAM_DICDI"           
##  [55] "tr|P90532|P90532_DICDI"           "sp|P54647|VATA_DICDI"            
##  [57] "sp|O97470|ADT_DICDI"              "sp|P83401|AL7A1_DICDI"           
##  [59] "sp|O77229|CATA_DICDI"             "sp|Q86L14|PUR9_DICDI"            
##  [61] "sp|Q54XS2|ACON_DICDI"             "sp|Q54Z26|GLYC1_DICDI"           
##  [63] "tr|Q54P24|Q54P24_DICDI"           "sp|Q86IA3|PDI1_DICDI"            
##  [65] "sp|Q55C16|UBA1_DICDI"             "sp|P54659|MVPB_DICDI"            
##  [67] "sp|Q54HB2|EFTU_DICDI"             "sp|Q54Z69|RL4_DICDI"             
##  [69] "tr|Q54F16|Q54F16_DICDI"           "sp|O76856|CATD_DICDI"            
##  [71] "sp|Q76NU1|VATB_DICDI"             "sp|Q54J47|PDX1_DICDI"            
##  [73] "sp|Q54X49|METE_DICDI"             "sp|Q01501|VDAC_DICDI"            
##  [75] "sp|Q8T869|BIP2_DICDI"             "sp|Q8TA03|6PGD_DICDI"            
##  [77] "sp|Q6TMK3|HSP88_DICDI"            "sp|O00780|VATE_DICDI"            
##  [79] "sp|Q557H1|DPP3_DICDI"             "tr|Q55CY7|Q55CY7_DICDI"          
##  [81] "sp|Q54EW8|DLDH_DICDI"             "sp|Q9GPM4|PGK_DICDI"             
##  [83] "sp|Q75JD5|PCKA_DICDI"             "sp|Q54YA0|ACLY_DICDI"            
##  [85] "sp|Q54I10|MMSA_DICDI"             "sp|P34118|MVPA_DICDI"            
##  [87] "sp|Q54WR9|GLNA3_DICDI"            "sp|Q54KB7|DHE3_DICDI"            
##  [89] "sp|P24005|ACTB_DICDI"             "sp|P54654|CAP_DICDI"             
##  [91] "sp|Q76NV5|HPPD_DICDI"             "sp|Q54BF6|MCFN_DICDI"            
##  [93] "sp|Q54RA2|AL4A1_DICDI"            "sp|Q554S6|ACT17_DICDI"           
##  [95] "sp|Q54QQ0|IMDH_DICDI"             "sp|P25870|CLH_DICDI"             
##  [97] "sp|Q54SF7|AATC_DICDI"             "sp|Q75JR3|IDHC_DICDI"            
##  [99] "sp|P33519|RAN_DICDI"              "tr|Q75JY8|Q75JY8_DICDI"          
## [101] "sp|Q54ZW5|RS3A_DICDI"             "sp|Q54JE4|ODO1_DICDI"            
## [103] "sp|P36408|GBB_DICDI"              "sp|Q9NKX1|ENPL_DICDI"            
## [105] "tr|Q557C7|Q557C7_DICDI"           "tr|Q86HU8|Q86HU8_DICDI"          
## [107] "sp|Q552J0|TCPQ_DICDI"             "sp|P27133|CORO_DICDI"            
## [109] "sp|Q869S7|SUCB2_DICDI"            "sp|O96621|ARP2_DICDI"            
## [111] "sp|Q54X73|ACOC_DICDI"             "sp|Q54EW2|Y9130_DICDI"           
## [113] "sp|P22685|RLA0_DICDI"             "tr|Q553T0|Q553T0_DICDI"          
## [115] "sp|Q54I98|SMT1_DICDI"             "tr|Q55CT4|Q55CT4_DICDI"          
## [117] "sp|Q9NKW1|MFEA_DICDI"             "sp|Q54K32|RGAA_DICDI"            
## [119] "sp|P21900|PURA_DICDI"             "sp|P34113|RL3_DICDI"             
## [121] "tr|Q54BI8|Q54BI8_DICDI"           "sp|Q55BY1|RSSA_DICDI"            
## [123] "sp|Q869Y7|ODO2_DICDI"             "sp|Q554D9|SYNC_DICDI"            
## [125] "sp|Q54DF1|ATPG_DICDI"             "sp|Q54YT4|MECR_DICDI"            
## [127] "tr|Q86IY4|Q86IY4_DICDI"           "sp|Q54LT2|URIC_DICDI"            
## [129] "sp|Q54ZD1|RL7A_DICDI"             "sp|P32256|TBB_DICDI"             
## [131] "sp|Q55AI5|SUCB1_DICDI"            "sp|Q55EQ3|Y9086_DICDI"           
## [133] "tr|Q54L07|Q54L07_DICDI"           "sp|Q54UU3|RS6_DICDI"             
## [135] "sp|Q54JP5|OAT_DICDI"              "tr|Q55FM7|Q55FM7_DICDI"          
## [137] "sp|Q54KB8|SYEC_DICDI"             "sp|P11874|RL7_DICDI"             
## [139] "sp|Q54M18|ARG56_DICDI"            "tr|Q54P64|Q54P64_DICDI"          
## [141] "tr|Q54JD4|Q54JD4_DICDI"           "sp|Q54MB5|ADK_DICDI"             
## [143] "sp|P42528|ARP3_DICDI"             "sp|P34093|NDKM_DICDI"            
## [145] "sp|P54661|SMLA_DICDI"             "tr|Q54X02|Q54X02_DICDI"          
## [147] "tr|Q54WH0|Q54WH0_DICDI"           "sp|Q54JM5|PSMD1_DICDI"           
## [149] "tr|Q54Q30|Q54Q30_DICDI"           "sp|Q54DK1|SQRD_DICDI"            
## [151] "sp|Q54N83|SYLC_DICDI"             "sp|Q54UH8|SERA_DICDI"            
## [153] "sp|Q54Y20|SYA_DICDI"              "sp|P0A6N1|EFTU_ECOLI"            
## [155] "sp|Q54QE4|PURCE_DICDI"            "tr|Q55GC0|Q55GC0_DICDI"          
## [157] "sp|Q54VG4|SGT_DICDI"              "tr|Q55EX9|Q55EX9_DICDI"          
## [159] "sp|Q55GQ5|SODC1_DICDI"            "sp|Q54G21|FKBP5_DICDI"           
## [161] "sp|Q54BM2|PAP1A_DICDI"            "sp|P36967|SUCA_DICDI"            
## [163] "sp|P36411|RAB7A_DICDI"            "sp|Q54BC6|PSMD2_DICDI"           
## [165] "sp|P51405|RS4_DICDI"              "tr|Q54PF9|Q54PF9_DICDI"          
## [167] "sp|P11872|M3R_DICDI"              "sp|P13231|HATA_DICDI"            
## [169] "sp|Q54EN4|PDI2_DICDI"             "sp|Q54E49|DDX6_DICDI"            
## [171] "sp|Q54GT6|SPYA_DICDI"             "tr|Q553S7|Q553S7_DICDI"          
## [173] "sp|Q9U641|CMFB_DICDI"             "tr|Q54TY4|Q54TY4_DICDI"          
## [175] "sp|Q54E04|VATM_DICDI"             "sp|Q55F21|AATM_DICDI"            
## [177] "sp|Q54RA8|ATPO_DICDI"             "sp|P46800|GBLP_DICDI"            
## [179] "sp|Q00766|PHS1_DICDI"             "sp|Q55FI1|GABT_DICDI"            
## [181] "sp|Q54KD9|RANG_DICDI"             "sp|Q54YD4|SYIC_DICDI"            
## [183] "sp|Q54E24|RS8_DICDI"              "sp|P46794|CBS_DICDI"             
## [185] "sp|O96623|ARPC2_DICDI"            "sp|Q55FT1|DPYD_DICDI"            
## [187] "sp|Q54GJ2|PUR2_DICDI"             "sp|Q5V9F0|AMPL_DICDI"            
## [189] "sp|P14132|RS9_DICDI"              "sp|Q54J66|SYTC1_DICDI"           
## [191] "sp|Q54DD2|THOPL_DICDI"            "sp|Q54D63|RL6_DICDI"             
## [193] "sp|Q55DR6|FCSA_DICDI"             "sp|P54641|VA0D_DICDI"            
## [195] "sp|Q54XX3|RL5_DICDI"              "sp|Q54DA8|STIP1_DICDI"           
## [197] "sp|Q54J97|CH60_DICDI"             "sp|Q54Q51|RS16_DICDI"            
## [199] "sp|Q54V77|PYRG_DICDI"             "sp|P09556|PYR5_DICDI"            
## [201] "sp|O60952|LIME_DICDI"             "tr|Q86AQ3|Q86AQ3_DICDI"          
## [203] "sp|P90526|RS3_DICDI"              "tr|O76187|O76187_DICDI"          
## [205] "sp|P0A910|OMPA_ECOLI"             "sp|Q54HG2|CTXA_DICDI"            
## [207] "sp|P54648|VATC_DICDI"             "tr|Q54DX3|Q54DX3_DICDI"          
## [209] "sp|Q54KZ8|EIF3M_DICDI"            "sp|P52922|LKHA4_DICDI"           
## [211] "tr|Q55CR6|Q55CR6_DICDI"           "sp|Q557J6|DBNL_DICDI"            
## [213] "sp|Q1ZXG4|PRLA_DICDI"             "sp|Q54D07|CY1_DICDI"             
## [215] "sp|Q54VM2|MDHC_DICDI"             "sp|Q86KD1|CAND1_DICDI"           
## [217] "tr|Q75K16|Q75K16_DICDI"           "sp|Q86KU2|SYVC_DICDI"            
## [219] "sp|Q9UAG7|FHBA_DICDI"             "tr|Q54PA2|Q54PA2_DICDI"          
## [221] "sp|Q9U3X4|DHSA_DICDI"             "sp|Q95VZ3|CARML_DICDI"           
## [223] "sp|P32073|GUAA_DICDI"             "tr|Q86K89|Q86K89_DICDI"          
## [225] "sp|Q6IMN8|ALRA_DICDI"             "sp|Q54C70|ODPA_DICDI"            
## [227] "tr|Q54XR4|Q54XR4_DICDI"           "sp|P10733|SEVE_DICDI"            
## [229] "tr|Q54G77|Q54G77_DICDI"           "sp|Q75JI3|NSF_DICDI"             
## [231] "sp|P16168|RL11_DICDI"             "tr|Q54FH4|Q54FH4_DICDI"          
## [233] "sp|Q55CT5|SEC31_DICDI"            "sp|Q86L05|RL10A_DICDI"           
## [235] "sp|Q964D8|BUP1_DICDI"             "tr|Q54N76|Q54N76_DICDI"          
## [237] "sp|P14329|RL19_DICDI"             "sp|Q54E20|RL13_DICDI"            
## [239] "sp|Q86K01|RL15_DICDI"             "sp|Q54QS3|DDX3_DICDI"            
## [241] "tr|Q54KZ1|Q54KZ1_DICDI"           "sp|Q54J69|RL10_DICDI"            
## [243] "sp|Q555Q9|GLGB_DICDI"             "sp|Q54PV8|IPYR_DICDI"            
## [245] "sp|Q54UP4|TALDO_DICDI"            "sp|Q54YZ0|UGPA2_DICDI"           
## [247] "sp|P34144|RAC1A_DICDI"            "sp|P20790|RAB8A_DICDI"           
## [249] "tr|Q556G1|Q556G1_DICDI"           "sp|Q86AS5|PPCE_DICDI"            
## [251] "sp|Q54J34|PUR8_DICDI"             "sp|P36410|RAB14_DICDI"           
## [253] "sp|P27685|RS2_DICDI"              "tr|Q55AN3|Q55AN3_DICDI"          
## [255] "sp|P54680|FIMB_DICDI"             "sp|Q54UF7|LDHD_DICDI"            
## [257] "sp|O96622|ARPC1_DICDI"            "sp|Q55E60|PEPD_DICDI"            
## [259] "tr|Q55F70|Q55F70_DICDI"           "sp|Q54BQ3|RL23A_DICDI"           
## [261] "sp|P14325|SYQ_DICDI"              "sp|P13022|CAPZA_DICDI"           
## [263] "tr|Q54U95|Q54U95_DICDI"           "sp|P13651|IF5A_DICDI"            
## [265] "sp|Q54JD9|SCOT_DICDI"             "sp|Q54VG0|DHTK1_DICDI"           
## [267] "sp|P34098|MANA_DICDI"             "tr|Q54WL7|Q54WL7_DICDI"          
## [269] "tr|Q54NV9|Q54NV9_DICDI"           "sp|P08799|MYS2_DICDI"            
## [271] "tr|Q7KWR1|Q7KWR1_DICDI"           "sp|Q54UJ0|PSD12_DICDI"           
## [273] "sp|Q54D73|FHBB_DICDI"             "sp|Q54PA9|PRPSA_DICDI"           
## [275] "sp|Q54C24|VPS35_DICDI"            "sp|P36413|ODP2_DICDI"            
## [277] "tr|Q8T131|Q8T131_DICDI"           "sp|Q55BZ4|PCY2_DICDI"            
## [279] "sp|P54686|WD42_DICDI"             "sp|Q86IV4|Y4775_DICDI"           
## [281] "sp|Q54IT3|AOFA_DICDI"             "sp|P60422|RL2_ECOLI"             
## [283] "sp|P15808|THY1_DICDI"             "sp|P18613|RAPA_DICDI"            
## [285] "sp|Q54QJ9|KAD2_DICDI"             "tr|Q54QK0|Q54QK0_DICDI"          
## [287] "sp|Q75JQ1|SYDC1_DICDI"            "sp|Q55C75|PSMD6_DICDI"           
## [289] "sp|P90521|K6PF_DICDI"             "tr|Q54TD0|Q54TD0_DICDI"          
## [291] "sp|Q5XM24|APRA_DICDI"             "sp|Q55BI2|IDHA_DICDI"            
## [293] "sp|Q869Q3|NAPA_DICDI"             "tr|Q54GL5|Q54GL5_DICDI"          
## [295] "tr|Q86JG3|Q86JG3_DICDI"           "sp|Q54WI8|PSD7_DICDI"            
## [297] "sp|Q8T2K9|MASY_DICDI"             "sp|Q86KU6|MTD1_DICDI"            
## [299] "tr|Q55ET7|Q55ET7_DICDI"           "sp|Q54QX3|CSN1_DICDI"            
## [301] "sp|Q86AD9|THIL1_DICDI"            "sp|Q54SM3|PPIA_DICDI"            
## [303] "sp|Q54HL0|COPG_DICDI"             "sp|Q54RF5|KPYK_DICDI"            
## [305] "tr|Q54T96|Q54T96_DICDI"           "sp|Q54P71|Y4755_DICDI"           
## [307] "sp|Q1ZXD3|PSMD3_DICDI"            "tr|Q54M03|Q54M03_DICDI"          
## [309] "sp|Q54KM7|GCSP_DICDI"             "sp|Q54VA2|FUMH_DICDI"            
## [311] "tr|Q55FM2|Q55FM2_DICDI"           "tr|Q75JL7|Q75JL7_DICDI"          
## [313] "sp|Q23919|PGM1_DICDI"             "sp|B0M0P5|DDB1_DICDI"            
## [315] "tr|Q75JW5|Q75JW5_DICDI"           "tr|Q54T94|Q54T94_DICDI"          
## [317] "sp|Q54NG2|RL17_DICDI"             "tr|Q54QS2|Q54QS2_DICDI"          
## [319] "tr|Q54JZ3|Q54JZ3_DICDI"           "tr|Q54D66|Q54D66_DICDI"          
## [321] "sp|Q55EK2|C524A_DICDI"            "sp|Q54Z09|RL14_DICDI"            
## [323] "tr|Q54M58|Q54M58_DICDI"           "sp|Q54X95|SYMC_DICDI"            
## [325] "sp|Q54SE2|PRDXL_DICDI"            "sp|Q550D2|SYFB_DICDI"            
## [327] "sp|Q54EW3|IPO5_DICDI"             "tr|Q55D63|Q55D63_DICDI"          
## [329] "tr|Q54C34|Q54C34_DICDI"           "sp|P25323|MYLKA_DICDI"           
## [331] "tr|Q54JA0|Q54JA0_DICDI"           "tr|Q55CJ9|Q55CJ9_DICDI"          
## [333] "sp|Q54I90|NDUV1_DICDI"            "sp|Q54PX9|RS12_DICDI"            
## [335] "sp|Q55CA0|VPS26_DICDI"            "sp|Q9NGQ2|KIF1_DICDI"            
## [337] "sp|Q86HX0|ODPB_DICDI"             "tr|Q54HZ2|Q54HZ2_DICDI"          
## [339] "sp|Q54Q48|Y5844_DICDI"            "sp|Q54NB6|FKBP4_DICDI"           
## [341] "sp|P02886|DIS1A_DICDI"            "sp|P36412|RB11A_DICDI"           
## [343] "tr|Q54FU0|Q54FU0_DICDI"           "sp|Q65YR8|CYTA1_DICDI"           
## [345] "sp|Q94504|CYSP7_DICDI"            "sp|Q54GE6|MDHA_DICDI"            
## [347] "sp|Q8T2H0|FAM49_DICDI"            "sp|Q54B67|MCFZ_DICDI"            
## [349] "tr|Q54Z72|Q54Z72_DICDI"           "sp|Q553B6|NMT_DICDI"             
## [351] "sp|O00909|ARF1_DICDI"             "sp|Q55DB4|T23O_DICDI"            
## [353] "sp|Q54EG3|RS14_DICDI"             "sp|Q54NP6|SNAA_DICDI"            
## [355] "sp|Q559Z0|NDUA9_DICDI"            "sp|Q86A72|Y4781_DICDI"           
## [357] "sp|Q54K67|MANG_DICDI"             "sp|Q54PJ1|PRS10_DICDI"           
## [359] "sp|Q54C27|OST1_DICDI"             "sp|Q54NE6|PGAM_DICDI"            
## [361] "tr|Q54F09|Q54F09_DICDI"           "sp|Q34312|NDUS1_DICDI"           
## [363] "sp|P54653|CBP2_DICDI"             "sp|Q54M70|DNPEP_DICDI"           
## [365] "tr|Q7KWS3|Q7KWS3_DICDI"           "tr|Q54VB8|Q54VB8_DICDI"          
## [367] "tr|Q86K67|Q86K67_DICDI"           "sp|Q54VZ4|RL18_DICDI"            
## [369] "sp|P0A7L0|RL1_ECOLI"              "sp|O77082|RS10_DICDI"            
## [371] "tr|Q75JT6|Q75JT6_DICDI"           "sp|P0A6M8|EFG_ECOLI"             
## [373] "tr|Q54FT2|Q54FT2_DICDI"           "sp|Q5V9E9|G6PI_DICDI"            
## [375] "sp|Q553M7|RL13A_DICDI"            "sp|O96625|ARPC4_DICDI"           
## [377] "sp|Q54HG9|RPN2_DICDI"             "sp|Q54GQ6|ACOX1_DICDI"           
## [379] "tr|Q54W88|Q54W88_DICDI"           "tr|Q86KZ6|Q86KZ6_DICDI"          
## [381] "sp|Q9GS21|RL28_DICDI"             "sp|Q55F34|DPNP_DICDI"            
## [383] "sp|P63284|CLPB_ECOLI"             "sp|Q1ZXQ1|FAAA_DICDI"            
## [385] "sp|Q54NQ0|PSD13_DICDI"            "tr|Q55GT3|Q55GT3_DICDI"          
## [387] "sp|Q54BC8|PSB5_DICDI"             "sp|Q54NJ8|HPRT_DICDI"            
## [389] "sp|Q54XF7|CUL5_DICDI"             "sp|Q559R0|SAR1A_DICDI"           
## [391] "sp|Q54CX6|3HIDH_DICDI"            "sp|Q9NCL8|PITP1_DICDI"           
## [393] "sp|P13021|CAPZB_DICDI"            "sp|Q54UU8|TRXB_DICDI"            
## [395] "sp|Q54KS8|SYFA_DICDI"             "sp|Q54MA6|RS5_DICDI"             
## [397] "sp|Q9TW32|PPIB_DICDI"             "sp|Q7YZN9|ERF3_DICDI"            
## [399] "sp|Q556U6|BIP1_DICDI"             "tr|Q54IU0|Q54IU0_DICDI"          
## [401] "tr|Q54S30|Q54S30_DICDI"           "sp|Q1ZXH9|CP51_DICDI"            
## [403] "sp|Q869T1|TWF_DICDI"              "sp|Q54N47|BCAT_DICDI"            
## [405] "sp|Q54X53|RL21_DICDI"             "tr|Q54TS5|Q54TS5_DICDI"          
## [407] "sp|Q54X97|EIF3C_DICDI"            "sp|Q55BE6|RL27_DICDI"            
## [409] "sp|Q869Z4|PCKGM_DICDI"            "tr|Q86IB4|Q86IB4_DICDI"          
## [411] "sp|Q94502|GANAB_DICDI"            "tr|Q54II1|Q54II1_DICDI"          
## [413] "tr|Q54F90|Q54F90_DICDI"           "sp|Q869N9|IF2A_DICDI"            
## [415] "tr|Q54UM3|Q54UM3_DICDI"           "tr|O96455|O96455_DICDI (+1)"     
## [417] "sp|Q7YXU4|CPNA_DICDI"             "sp|Q54RX6|TCTP1_DICDI"           
## [419] "sp|Q54XD8|IF2G_DICDI"             "tr|Q54E73|Q54E73_DICDI"          
## [421] "sp|P0AG55|RL6_ECOLI"              "tr|Q54JS9|Q54JS9_DICDI"          
## [423] "sp|Q54TR8|NACB_DICDI"             "sp|Q55E54|COROB_DICDI"           
## [425] "sp|Q54MJ7|ALAM_DICDI"             "sp|Q23862|RACE_DICDI"            
## [427] "sp|P48160|RL27A_DICDI"            "sp|P16894|GPA1_DICDI"            
## [429] "tr|Q76P15|Q76P15_DICDI"           "tr|Q8T2R4|Q8T2R4_DICDI"          
## [431] "sp|P13023|RL8_DICDI"              "sp|Q54XS1|PH4H_DICDI"            
## [433] "sp|Q54KR1|SYCC_DICDI"             "sp|P03023|LACI_ECOLI"            
## [435] "tr|Q55F80|Q55F80_DICDI"           "sp|Q54KE6|MCCA_DICDI"            
## [437] "sp|Q54JL3|FTCD_DICDI"             "tr|Q54G53|Q54G53_DICDI"          
## [439] "tr|Q869X1|Q869X1_DICDI"           "sp|Q54I41|RS7_DICDI"             
## [441] "sp|Q54MK8|RL18A_DICDI"            "sp|Q54B68|IDHB_DICDI"            
## [443] "tr|Q54DD1|Q54DD1_DICDI"           "sp|Q86AS6|SYHC_DICDI"            
## [445] "sp|Q54LV3|EFTS_DICDI"             "sp|Q55ED1|NAP1_DICDI"            
## [447] "sp|Q55BJ9|SODM_DICDI"             "sp|P0A9B2|G3P1_ECOLI"            
## [449] "tr|Q54PL1|Q54PL1_DICDI"           "sp|Q54S90|RS11_DICDI"            
## [451] "sp|Q54EW1|GLYC2_DICDI"            "sp|Q55G04|PSA5_DICDI"            
## [453] "tr|Q54CA6|Q54CA6_DICDI"           "sp|P60723|RL4_ECOLI"             
## [455] "tr|Q54UV0|Q54UV0_DICDI"           "sp|Q54RB9|CMC_DICDI"             
## [457] "sp|Q54N17|RS15_DICDI"             "sp|Q76P23|PM34_DICDI"            
## [459] "sp|Q54T59|SEC23_DICDI"            "tr|Q54E45|Q54E45_DICDI"          
## [461] "sp|O96624|ARPC3_DICDI"            "tr|Q54HR9|Q54HR9_DICDI"          
## [463] "sp|Q54TL8|RS26_DICDI"             "sp|Q54PM7|NAGK_DICDI"            
## [465] "tr|Q86IF6|Q86IF6_DICDI"           "tr|Q54JS1|Q54JS1_DICDI"          
## [467] "tr|Q8MMS1|Q8MMS1_DICDI"           "sp|Q54QM8|RL26_DICDI"            
## [469] "sp|Q94465|GCH1_DICDI"             "tr|Q54RW1|Q54RW1_DICDI"          
## [471] "sp|Q869U7|RS18_DICDI"             "tr|Q551V0|Q551V0_DICDI"          
## [473] "sp|Q54Y41|RS20_DICDI"             "sp|Q55FK4|APT12_DICDI"           
## [475] "sp|Q54U07|NACA_DICDI"             "sp|O96759|ADAS_DICDI"            
## [477] "sp|Q54NC1|NCB5R_DICDI"            "tr|Q55BV1|Q55BV1_DICDI"          
## [479] "tr|Q869Z5|Q869Z5_DICDI"           "sp|P0A7R1|RL9_ECOLI"             
## [481] "sp|Q54X03|PMM1_DICDI"             "sp|Q54FD7|ETFA_DICDI"            
## [483] "sp|Q86A21|PSB1_DICDI"             "sp|Q54XI5|RL9_DICDI"             
## [485] "sp|Q54YN2|MAAI_DICDI"             "sp|Q54QR3|RB32A_DICDI"           
## [487] "sp|Q54QR2|PSB7_DICDI"             "sp|Q55E06|HEM2_DICDI"            
## [489] "tr|Q9BI24|Q9BI24_DICDI"           "sp|Q54MB4|ASNS_DICDI"            
## [491] "sp|Q556N5|ADRM1_DICDI"            "sp|Q54RE8|KMO_DICDI"             
## [493] "tr|Q54R90|Q54R90_DICDI"           "tr|Q869N7|Q869N7_DICDI"          
## [495] "sp|Q54XC1|5NTC_DICDI"             "tr|Q54DZ8|Q54DZ8_DICDI"          
## [497] "sp|Q75K27|RS24_DICDI"             "sp|Q54MR1|GLO2_DICDI"            
## [499] "tr|Q54F74|Q54F74_DICDI"           "sp|Q54G86|RL23_DICDI"            
## [501] "tr|Q54XI2|Q54XI2_DICDI (+1)"      "sp|Q54XK2|SC61A_DICDI"           
## [503] "sp|Q86A77|VATD_DICDI"             "sp|Q5TJ65|VASP_DICDI"            
## [505] "sp|Q54YD8|COPB2_DICDI"            "sp|Q86A17|DHPR_DICDI"            
## [507] "sp|Q55CQ6|SERC_DICDI"             "sp|Q86KI1|AP2A2_DICDI"           
## [509] "sp|Q54JD2|Y8137_DICDI"            "sp|Q54RR5|ACDSB_DICDI"           
## [511] "sp|Q869R8|TPIS_DICDI"             "sp|Q54K91|ACH1_DICDI"            
## [513] "sp|Q54QW1|EIF3B_DICDI"            "sp|P61889|MDH_ECOLI"             
## [515] "tr|Q869L6|Q869L6_DICDI"           "sp|Q54CJ3|6PGL_DICDI"            
## [517] "sp|P0A7J3|RL10_ECOLI"             "sp|Q55DY7|PSB2_DICDI"            
## [519] "sp|Q54XM7|PSA6_DICDI"             "sp|Q559X6|RAB2B_DICDI"           
## [521] "tr|Q86I62|Q86I62_DICDI"           "sp|Q27562|PSA1_DICDI"            
## [523] "tr|Q9NH03|Q9NH03_DICDI"           "sp|Q54BM7|PPK_DICDI"             
## [525] "sp|P34119|PSA4_DICDI"             "tr|Q54Q74|Q54Q74_DICDI"          
## [527] "sp|P42520|RS17_DICDI"             "sp|Q55C99|SYDM_DICDI"            
## [529] "sp|Q54X51|RS19_DICDI"             "tr|Q86J04|Q86J04_DICDI"          
## [531] "sp|Q54RX9|RAB5B_DICDI"            "sp|P06959|ODP2_ECOLI"            
## [533] "tr|Q54PW3|Q54PW3_DICDI"           "tr|Q555X7|Q555X7_DICDI"          
## [535] "sp|Q6TU48|MAOX_DICDI"             "sp|Q1ZXF1|ECHM_DICDI"            
## [537] "tr|Q54CW1|Q54CW1_DICDI"           "tr|Q75JE7|Q75JE7_DICDI"          
## [539] "sp|Q86AD5|Y1564_DICDI"            "sp|P34136|HMDH2_DICDI"           
## [541] "sp|Q8T1V6|NDUS4_DICDI"            "sp|Q1ZXQ4|FCSB_DICDI"            
## [543] "sp|Q8T137|GSHR_DICDI"             "sp|P34142|RAB21_DICDI"           
## [545] "sp|Q55C77|FCL_DICDI"              "sp|Q54NZ7|ALRB_DICDI"            
## [547] "sp|Q1ZXF7|GMDS_DICDI"             "sp|Q54PF3|CSN5_DICDI"            
## [549] "sp|O15706|VACA_DICDI"             "tr|Q55D50|Q55D50_DICDI"          
## [551] "sp|Q54JQ2|IDE_DICDI"              "sp|P34120|PSA7_DICDI"            
## [553] "sp|Q54K39|GMPPB_DICDI"            "sp|P0A6Z3|HTPG_ECOLI"            
## [555] "sp|Q55GJ6|PSB6_DICDI"             "sp|P54201|UBPA_DICDI"            
## [557] "sp|Q55D66|PSB3_DICDI"             "sp|Q54IF7|VPS29_DICDI"           
## [559] "sp|Q54EQ1|EIF3K_DICDI"            "sp|Q54NU2|RAB1D_DICDI"           
## [561] "tr|O15744|O15744_DICDI"           "sp|Q86IJ1|PSDE_DICDI"            
## [563] "tr|Q54QE7|Q54QE7_DICDI"           "sp|Q55FK2|RAB6_DICDI"            
## [565] "sp|Q55G10|PNCB_DICDI"             "tr|Q54P88|Q54P88_DICDI"          
## [567] "sp|Q9U9A3|PPP6_DICDI"             "sp|Q54SV3|ALN1_DICDI"            
## [569] "sp|Q54ML1|NADE_DICDI"             "tr|Q54HG8|Q54HG8_DICDI"          
## [571] "sp|P0AG67|RS1_ECOLI"              "sp|Q54DG1|ALDH3_DICDI"           
## [573] "sp|Q54VG1|GPA12_DICDI"            "sp|Q54QG9|UBA3_DICDI"            
## [575] "tr|Q54T87|Q54T87_DICDI"           "sp|P02413|RL15_ECOLI"            
## [577] "tr|Q86I47|Q86I47_DICDI"           "sp|Q54YZ4|ETFB_DICDI"            
## [579] "sp|P02359|RS7_ECOLI"              "sp|Q8T2J9|MCCB_DICDI"            
## [581] "sp|P32253|RASC_DICDI"             "tr|Q54N71|Q54N71_DICDI"          
## [583] "sp|P0A9Q7|ADHE_ECOLI"             "tr|Q75JS7|Q75JS7_DICDI"          
## [585] "sp|Q54J23|RL35_DICDI"             "sp|Q54DM7|PSA2_DICDI"            
## [587] "tr|Q54FV6|Q54FV6_DICDI"           "tr|Q86HW2|Q86HW2_DICDI"          
## [589] "sp|P34139|RAB1A_DICDI"            "sp|Q9Y0B7|PP4C_DICDI"            
## [591] "tr|Q54FY2|Q54FY2_DICDI"           "sp|Q54F10|NDUV2_DICDI"           
## [593] "tr|Q54MF0|Q54MF0_DICDI"           "sp|Q54DY1|ARGJ_DICDI"            
## [595] "sp|P32254|RASS_DICDI"             "sp|Q55FU2|COPE_DICDI"            
## [597] "sp|P0C7B6|GLNA2_DICDI (+1)"       "sp|Q54MP2|CCD22_DICDI"           
## [599] "sp|Q75JX0|NADC_DICDI"             "sp|Q54CC5|EIF3E_DICDI"           
## [601] "sp|Q54PH8|RS13_DICDI"             "tr|Q55D72|Q55D72_DICDI"          
## [603] "sp|Q54B82|CSN4_DICDI"             "tr|Q55GC5|Q55GC5_DICDI"          
## [605] "tr|Q54IU1|Q54IU1_DICDI"           "tr|Q54GQ7|Q54GQ7_DICDI"          
## [607] "sp|Q54DD0|AMPD_DICDI"             "sp|Q54II8|U553_DICDI"            
## [609] "tr|Q54T47|Q54T47_DICDI"           "sp|Q54C92|CSN6_DICDI"            
## [611] "sp|P32252|RASB_DICDI"             "sp|P0A799|PGK_ECOLI"             
## [613] "tr|Q86JB5|Q86JB5_DICDI"           "tr|Q8T849|Q8T849_DICDI"          
## [615] "sp|Q54IK1|RRAGA_DICDI"            "tr|Q54ES4|Q54ES4_DICDI"          
## [617] "sp|Q55AB5|RL32_DICDI"             "tr|Q54U01|Q54U01_DICDI"          
## [619] "sp|Q55C72|U587_DICDI"             "sp|Q55C21|AMPM2_DICDI"           
## [621] "tr|Q54VU3|Q54VU3_DICDI"           "sp|Q55A19|RS23_DICDI"            
## [623] "tr|Q54C69|Q54C69_DICDI"           "sp|Q86KZ5|SBDS_DICDI"            
## [625] "sp|Q869N6|CRTL_DICDI"             "tr|Q54SQ0|Q54SQ0_DICDI"          
## [627] "sp|Q9XZE5|PP2AA_DICDI"            "sp|Q54BM3|MCFG_DICDI"            
## [629] "sp|Q54EJ5|GLOB2_DICDI"            "sp|Q55E13|ZPR1_DICDI"            
## [631] "tr|Q54C73|Q54C73_DICDI"           "sp|P0ABK5|CYSK_ECOLI"            
## [633] "tr|Q54G88|Q54G88_DICDI"           "sp|Q54J50|RL12_DICDI"            
## [635] "sp|Q75K24|CSN8_DICDI"             "tr|Q54W38|Q54W38_DICDI"          
## [637] "tr|Q54WP6|Q54WP6_DICDI"           "tr|Q54BX7|Q54BX7_DICDI"          
## [639] "sp|P54706|COF1_DICDI"             "sp|P34149|RACC_DICDI"            
## [641] "tr|Q58A42|Q58A42_DICDI"           "sp|P0AFG8|ODP1_ECOLI"            
## [643] "tr|Q55EJ0|Q55EJ0_DICDI"           "sp|Q556Q0|PSB4_DICDI"            
## [645] "tr|Q54JU2|Q54JU2_DICDI"           "sp|Q54D08|LST8_DICDI"            
## [647] "sp|Q54IM8|ACAD8_DICDI"            "sp|Q55FN7|ODBB_DICDI"            
## [649] "tr|Q54QC5|Q54QC5_DICDI"           "tr|B0G197|B0G197_DICDI"          
## [651] "sp|O96626|ARPC5_DICDI"            "sp|P0A7Z4|RPOA_ECOLI"            
## [653] "tr|Q54IW4|Q54IW4_DICDI"           "sp|Q54DP1|TKRA_DICDI"            
## [655] "sp|Q54XZ0|MFEB_DICDI"             "sp|Q54FL2|RABG2_DICDI"           
## [657] "tr|Q54I22|Q54I22_DICDI"           "sp|Q54S59|WDR61_DICDI"           
## [659] "sp|Q55GQ6|UPP_DICDI"              "sp|Q27563|PSA3_DICDI"            
## [661] "tr|Q8T8P2|Q8T8P2_DICDI"           "sp|Q54P23|SDF2_DICDI"            
## [663] "tr|Q86L27|Q86L27_DICDI"           "sp|Q54XM6|ETFD_DICDI"            
## [665] "tr|Q551A9|Q551A9_DICDI"           "tr|Q54G31|Q54G31_DICDI"          
## [667] "sp|Q8MQU6|CISYP_DICDI"            "sp|Q54DA9|HACL1_DICDI"           
## [669] "sp|Q1ZXE8|SRP68_DICDI"            "sp|Q54GP3|SPRE_DICDI"            
## [671] "sp|Q54MT0|EIF3I_DICDI"            "sp|Q54XH6|PHYD1_DICDI"           
## [673] "sp|P36409|RAB2A_DICDI"            "tr|Q55BS7|Q55BS7_DICDI"          
## [675] "tr|Q54RB5|Q54RB5_DICDI"           "tr|Q54CK4|Q54CK4_DICDI"          
## [677] "tr|Q55CE9|Q55CE9_DICDI"           "sp|Q86H45|ELP2_DICDI"            
## [679] "sp|Q54LV8|RL34_DICDI"             "tr|Q55E92|Q55E92_DICDI"          
## [681] "sp|Q86K21|CPNB_DICDI"             "sp|Q95YL5|PEFA_DICDI"            
## [683] "sp|Q86K94|TPPC3_DICDI"            "tr|Q54J53|Q54J53_DICDI"          
## [685] "sp|Q54G70|SODC5_DICDI"            "tr|Q54N53|Q54N53_DICDI"          
## [687] "sp|P0A6P1|EFTS_ECOLI"             "sp|Q54YJ6|IF1A_DICDI"

# use discern to get set difference
# use discern discern(c(a,b), c(c,d)) -> first takes union, then difference

Presence/absence protein

Heatmap for uniprot presence/absence over bait, condition or experiment. Filtered on protein

filterd <- filter(all_data_dicty, uniprot == 'sp|P0A9K9|SLYD_ECOLI')

condition <- split(filterd$uniprot, all_data_dicty$condition)

## Warning in split.default(filterd$uniprot, all_data_dicty$condition): data length
## is not a multiple of split variable

bait <- split(filterd$uniprot, all_data_dicty$bait)

## Warning in split.default(filterd$uniprot, all_data_dicty$bait): data length is
## not a multiple of split variable

toy_condition_filtered = Venn(condition)
setmap(toy_condition_filtered, element_clustering = FALSE, set_clustering = FALSE)

## Warning in vegan::vegdist(t(df), method = "jaccard"): you have empty rows: their
## dissimilarities may be meaningless in method "jaccard"

## Warning in vegan::vegdist(t(df), method = "jaccard"): missing values in results

toy_bait_filtered = Venn(bait)
setmap(toy_bait_filtered, element_clustering = FALSE, set_clustering = FALSE)

## Warning in vegan::vegdist(t(df), method = "jaccard"): you have empty rows: their
## dissimilarities may be meaningless in method "jaccard"

## Warning in vegan::vegdist(t(df), method = "jaccard"): missing values in results

Overlapping proteins

my_data <-all_data_dicty %>% 
  group_by(bait, condition) %>% 
  tidyr::unite(bait_condition, c(bait, condition), sep = "_")

count(my_data, bait_condition, uniprot) %>%
  spread(bait_condition, n, fill = 0) %>%
  select(-uniprot) %>%
  as.matrix() %>%
  crossprod()

##                  Galpha2_starv Galpha2_veg Galpha4_Normal Galpha8_GDP
## Galpha2_starv             1603        1603           1603        1059
## Galpha2_veg               1603        1603           1603        1059
## Galpha4_Normal            1603        1603           1603        1059
## Galpha8_GDP               1059        1059           1059        1436
## Galpha8_GppNHp            1059        1059           1059        1436
## Galpha8_Normal             957         957            957        1218
## Gbeta1_Normal              736         736            736         739
## Gbeta2_Normal              736         736            736         739
## Rac1_Normal               1098        1098           1098        1131
## RapA_Normal                  0           0              0           0
## RasB_Normal                609         609            609         567
## RasC_Normal                759         759            759         649
## RasG1_Normal               279         279            279         247
## Ric8_Normal               1098        1098           1098        1131
## Roco4_BACKGROUND          1098        1098           1098        1131
##                  Galpha8_GppNHp Galpha8_Normal Gbeta1_Normal Gbeta2_Normal
## Galpha2_starv              1059            957           736           736
## Galpha2_veg                1059            957           736           736
## Galpha4_Normal             1059            957           736           736
## Galpha8_GDP                1436           1218           739           739
## Galpha8_GppNHp             1436           1218           739           739
## Galpha8_Normal             1218           1228           692           692
## Gbeta1_Normal               739            692           876           876
## Gbeta2_Normal               739            692           876           876
## Rac1_Normal                1131           1015           749           749
## RapA_Normal                   0              0             0             0
## RasB_Normal                 567            515           443           443
## RasC_Normal                 649            586           526           526
## RasG1_Normal                247            220           217           217
## Ric8_Normal                1131           1015           749           749
## Roco4_BACKGROUND           1131           1015           749           749
##                  Rac1_Normal RapA_Normal RasB_Normal RasC_Normal RasG1_Normal
## Galpha2_starv           1098           0         609         759          279
## Galpha2_veg             1098           0         609         759          279
## Galpha4_Normal          1098           0         609         759          279
## Galpha8_GDP             1131           0         567         649          247
## Galpha8_GppNHp          1131           0         567         649          247
## Galpha8_Normal          1015           0         515         586          220
## Gbeta1_Normal            749           0         443         526          217
## Gbeta2_Normal            749           0         443         526          217
## Rac1_Normal             1448           0         577         679          264
## RapA_Normal                0         461           0           0            0
## RasB_Normal              577           0         808         570          241
## RasC_Normal              679           0         570         998          300
## RasG1_Normal             264           0         241         300          337
## Ric8_Normal             1448           0         577         679          264
## Roco4_BACKGROUND        1448           0         577         679          264
##                  Ric8_Normal Roco4_BACKGROUND
## Galpha2_starv           1098             1098
## Galpha2_veg             1098             1098
## Galpha4_Normal          1098             1098
## Galpha8_GDP             1131             1131
## Galpha8_GppNHp          1131             1131
## Galpha8_Normal          1015             1015
## Gbeta1_Normal            749              749
## Gbeta2_Normal            749              749
## Rac1_Normal             1448             1448
## RapA_Normal                0                0
## RasB_Normal              577              577
## RasC_Normal              679              679
## RasG1_Normal             264              264
## Ric8_Normal             1448             1448
## Roco4_BACKGROUND        1448             1448

# check value from crossproduct
#                          Galpha2_starv
#RasG1_Normal               279

bait_condition <- split(my_data$uniprot, my_data$bait_condition)
toy = Venn(bait_condition)
length(overlap(toy, c("Galpha2_starv", "RasG1_Normal")))

## [1] 279

# same number of proteins reported

Simple heatmap with clustering on overlapping proteins per experiment

my_data <- all_data_dicty %>% 
  group_by(bait, condition) %>% 
  tidyr::unite(bait_condition, c(bait, condition), sep = "_")

overlapping <- count(my_data, bait_condition, uniprot) %>%
  spread(bait_condition, n, fill = 0) %>%
  select(-uniprot) %>%
  as.matrix() %>%
  crossprod()

heatmap(overlapping)

ggplot heatmap overlapping proteins per experiment

overlap_long <- reshape2::melt(overlapping)
ggplot(overlap_long, aes(x = Var1, y = Var2, fill = value)) +
geom_tile() +
theme(axis.text.x = element_text(angle = 45, hjust = 1))

PCA

Experiment (bait + condition) taking raw spectral_count

my_data <- all_data_dicty %>% 
  group_by(bait, condition) %>% 
  tidyr::unite(bait_condition, c(bait, condition), sep = "_")

pivoted <- my_data %>% 
  select(uniprot, bait_condition, spectral_count) %>%
  group_by(bait_condition) %>%
  pivot_wider(names_from = uniprot, values_from = spectral_count, values_fill = 0) %>%
  summarise_all(funs(sum)) %>%
  tibble::column_to_rownames(var = "bait_condition") 

## Warning: `funs()` is deprecated as of dplyr 0.8.0.
## Please use a list of either functions or lambdas: 
## 
##   # Simple named list: 
##   list(mean = mean, median = median)
## 
##   # Auto named with `tibble::lst()`: 
##   tibble::lst(mean, median)
## 
##   # Using lambdas
##   list(~ mean(., trim = .2), ~ median(., na.rm = TRUE))
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_warnings()` to see where this warning was generated.

wdbc.pr <- prcomp(pivoted)
summary(wdbc.pr)

## Importance of components:
##                              PC1       PC2       PC3       PC4       PC5
## Standard deviation     1971.9458 1290.9757 838.30393 756.25286 636.05050
## Proportion of Variance    0.4743    0.2033   0.08572   0.06976   0.04935
## Cumulative Proportion     0.4743    0.6776   0.76331   0.83307   0.88242
##                              PC6       PC7       PC8       PC9      PC10
## Standard deviation     595.58323 440.54269 371.26426 355.02771 265.38000
## Proportion of Variance   0.04327   0.02367   0.01681   0.01537   0.00859
## Cumulative Proportion    0.92569   0.94936   0.96617   0.98154   0.99013
##                             PC11      PC12     PC13    PC14      PC15
## Standard deviation     204.91780 171.32312 93.43430 28.3651 5.069e-12
## Proportion of Variance   0.00512   0.00358  0.00106  0.0001 0.000e+00
## Cumulative Proportion    0.99526   0.99884  0.99990  1.0000 1.000e+00

screeplot(wdbc.pr, type = "l", npcs = 15, main = "Screeplot of the first 15 PCs")
abline(h = 1, col="red", lty=5)
legend("topright", legend=c("Eigenvalue = 1"),
       col=c("red"), lty=5, cex=0.6)

cumpro <- cumsum(wdbc.pr$sdev^2 / sum(wdbc.pr$sdev^2))
plot(cumpro[0:15], xlab = "PC #", ylab = "Amount of explained variance", main = "Cumulative variance plot")

#abline(v = 6, col="blue", lty=5)
#abline(h = 0.88759, col="blue", lty=5)
#legend("topleft", legend=c("Cut-off @ PC6"),col=c("blue"), lty=5, cex=0.6)


plot(wdbc.pr$x[,1],wdbc.pr$x[,2], xlab="PC1 (47.4%)", ylab = "PC2 (20.3%)", main = "PC1 / PC2 - plot")

library("factoextra")

## Welcome! Want to learn more? See two factoextra-related books at https://goo.gl/ve3WBa

fviz_pca_ind(wdbc.pr, geom.ind = "point", pointshape = 21, 
             pointsize = 2, 
             fill.ind = rownames(pivoted), 
             col.ind = "black", 
             palette = "ucscgb", 
            # addEllipses = TRUE,
             label = "var",
             col.var = "black",
             repel = TRUE,
             legend.title = "bait_condition") +
  ggtitle("2D PCA-plot") +
  theme(plot.title = element_text(hjust = 0.5))

Igraph network plot

library(igraph)

## 
## Attaching package: 'igraph'

## The following object is masked from 'package:tidyr':
## 
##     crossing

## The following objects are masked from 'package:dplyr':
## 
##     as_data_frame, groups, union

## The following objects are masked from 'package:stats':
## 
##     decompose, spectrum

## The following object is masked from 'package:base':
## 
##     union

library(visNetwork)

my_data <-all_data_dicty %>% group_by(bait, condition) %>% tidyr::unite(bait_condition, c(bait, condition), sep = "_")
x <- my_data %>% separate(uniprot, c("a", "b", "c", "protid", "genid", "source"), extra = "merge", fill = "left", sep = '[_|]')
x <- x %>% select(-one_of(c("a", "b", "c")))

# resulting in 17k+ interactions, hairball!, need to filter
new_x <- x %>% filter(spectral_count > 200)

nodes <- as.data.frame(unique(new_x$bait_condition))
nodes$shape = 'triangle'
colnames(nodes) <- c('id', 'shape')

nodes <- nodes %>% add_row(id = unique(new_x$genid), shape = 'circle')

#nodes <- nodes %>% add_row(id = unique(new_x$genid))
nodes$label <- nodes$id

# nodes (shapes) and edges (thickness  = width, use normalized counts) need to be done
# nodes scale (value) on basis of number of interactions
# gene ids, are not complete, <NA> or missing. Check the seperate function!


my_edges <- data.frame(new_x$bait_condition, new_x$genid, new_x$z_score_spectral)
colnames(my_edges) <- c('from', 'to', 'value')

graph <- graph_from_data_frame(my_edges, directed = FALSE)

## Warning in graph_from_data_frame(my_edges, directed = FALSE): In `d' `NA'
## elements were replaced with string "NA"

# color groups based on community detection, method louvain
#cluster <- cluster_louvain(graph)
#cluster_df <- data.frame(as.list(membership(cluster)))
#cluster_df <- as.data.frame(t(cluster_df))
#cluster_df$label <- rownames(cluster_df)
#nodes <- left_join(nodes, cluster_df, by = 'label')
#colnames(nodes)[3] <- 'group'

visNetwork(nodes = nodes, edges = my_edges) %>%
  visOptions(highlightNearest = list(enabled = TRUE, algorithm = "hierarchical", 
   degree = list(from = 1, to = 1)), nodesIdSelection = TRUE) %>%
  visPhysics(stabilization = FALSE, barnesHut = ) %>%
  visLayout(improvedLayout = TRUE)